BiCAT builds bimanual coordination directly into VLA action tokens
DJiafei · x · 2026-11-19
DJiafei introduces BiCAT (Bimanual Coordination Action Tokenization), a method that builds coordination directly into a VLA's action tokens.
The core argument: coordinating two arms takes more than knowing what to do — coordination must be modeled at the action-representation level. BiCAT suits high-demanding tasks requiring coordination and low latency (e.g. two-arm ball-handling demos).
Related event: BiCAT Encodes Bimanual Coordination Directly into VLA Action Tokens(10 posts)→
More from Embodied
- Robotics sim tips: calibrate your real robot first, never hand-tune sim parameters — jonstephens85 · 2026-11-19
- Embedl cuts Jetson Thor driving-plan latency from 603.7ms to 82.7ms without touching weights — AIFlow_ML · 2026-11-19
- NVIDIA ships Alpamayo 2 Edge: 2B reasoning VLA model running in-vehicle at 160-190ms latency — tomaszbednarz · 2026-11-19
- Game2Player Turns 568 Web Games Into Verifiable Training Grounds for Visual Agents — UIUC-CS · 2026-11-19
- NeoteAI open-sources 5,000 hours of real tactile data plus three tactile foundation reports — 青稞AI · 2026-11-19
- Musk predicts Tesla Optimus will wash, dry and put away dishes in 12-18 months — Polymarket · 2026-11-19